GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day)
10319bc verified Download tokenizer.json from bot-lab-21/GLM-5.3-Int4-Int8Mix-Pollard-GPTQ-MTP-Draft: direct link, hf CLI and curl.
- Browser
- Download file 20.2 MB
-
https://huggingface.co/bot-lab-21/GLM-5.3-Int4-Int8Mix-Pollard-GPTQ-MTP-Draft/resolve/main/tokenizer.json
- Command line
-
hf download hf://bot-lab-21/GLM-5.3-Int4-Int8Mix-Pollard-GPTQ-MTP-Draft/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/bot-lab-21/GLM-5.3-Int4-Int8Mix-Pollard-GPTQ-MTP-Draft/resolve/main/tokenizer.json
20.2 MB
- Xet hash:
- 961c851c73a3e1f213cece750e312f56f35412b14dd461536a2b2b9abc19aa33
- Size of remote file:
- 20.2 MB
- SHA256:
- 19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.